Revision History
Speech Recognition · 11 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Bring the speech recognition survey current through July 2026: add speech-encoder plus LLM-decoder and omni-model architectures, streaming and full-duplex systems, contamination and held-out evaluation, what WER does not capture, latency budgets and deployment cost, and the published work on accent, age, disordered-speech disparity and hallucinated transcription
Version 11 · Aug 1, 2026, 11:17 AM
- Correction: fix one grammar error and describe the Conformer block order precisely; retain the reviewed article structure, sources, links, identity, scope, redirect, and categories.
Version 10 · Jul 29, 2026, 01:56 AM
- Added 6 contextual internal links
Version 9 · Jul 23, 2026, 03:06 PM